Exploring Cross-Client Memorization of Training Data in Large Language Models for Federated Learning
Federated learning (FL) enables collaborative training without raw data sharing, but still risks training data memorization. Existing FL memorization detection techniques focus on one sample at a time, underestimating more subtle risks of cross-sample memorization. In contrast, recent work on centralized learning (CL) has introduced fine-grained methods to assess memorization across all samples in training data, but these assume centralized access to data and cannot be applied directly to FL. We bridge this gap by proposing a framework that quantifies both intra- and inter-client memorization in FL using fine-grained cross-sample memorization measurement across all clients. Based on this framework, we conduct two studies: (1) measuring subtle memorization across clients and (2) examining key factors that influence memorization, including decoding strategies, prefix length, and FL algorithms. Our findings reveal that FL models do memorize client data, particularly intra-client data, more than inter-client data, with memorization influenced by training and inferencing factors.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
Exploring Memorization in Fine-tuned Language Models
Large language models (LLMs) have shown great capabilities in various tasks but also exhibited memorization of training data, raising tremendous privacy and copyright concerns. While prior works have studied memorization…
MemorizationFedCVESA: Taking Away Training Data in Federated Learning via Correlation Value Encoding and Segmented Aggregation
Federated learning (FL) avoids explicit data exposure by keeping raw data on local clients, yet privacy risks remain in the training process and the learned model itself. Recently, centralized Taking Away Training Data (…
Federated LearningMitigating Unintended Memorization with LoRA in Federated Learning for LLMs
Federated learning (FL) is a popular paradigm for collaborative training which avoids direct data exposure between clients. However, data privacy issues still remain: FL-trained large language models are capable of memor…
Federated LearningMedical Question AnsweringMemorizationPrivacy Preserving+1Exploring Local Memorization in Diffusion Models via Bright Ending Attention
In this paper, we identify and leverage a novel `bright ending' (BE) anomaly in diffusion models prone to memorizing training images to address a new task: locating localized memorization regions within these models. BE …
MemorizationPreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language Models
Pre-trained Language Models such as BERT are impressive machines with the ability to memorize, possibly generalized learning examples. We present here a small, focused contribution to the analysis of the interplay betwee…
MemorizationRelation